快速入门MapReduc① 实现WordCount

目录

1.需要处理的数据

2.创建maven项目pom.xml

3.编写map类

4.编写Reduce类

5.编写启动类

6.执行的结果

---

1.需要处理的数据

hello word
word count
hello MapReduce

2.创建maven项目pom.xml

 <repositories>
        <repository>
            <id>cloudera</id>
            <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
        </repository>
    </repositories>
    <dependencies>
        <dependency>
            <groupId>org.apache.Hadoop</groupId>
            <artifactId>Hadoop-client</artifactId>
            <version>2.6.0-mr1-cdh5.14.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.Hadoop</groupId>
            <artifactId>Hadoop-common</artifactId>
            <version>2.6.0-cdh5.14.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.Hadoop</groupId>
            <artifactId>Hadoop-hdfs</artifactId>
            <version>2.6.0-cdh5.14.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.Hadoop</groupId>
            <artifactId>Hadoop-mapreduce-client-core</artifactId>
            <version>2.6.0-cdh5.14.0</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.11</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.testng</groupId>
            <artifactId>testng</artifactId>
            <version>RELEASE</version>
        </dependency>
    </dependencies>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.0</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                    <encoding>UTF-8</encoding>
                </configuration>
            </plugin>

            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>2.4.3</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <minimizeJar>true</minimizeJar>
                        </configuration>
                    </execution>
                </executions>
            </plugin>

        </plugins>
    </build>

3.编写map类

package com.czxy.wordCount;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class WordCountMapper extends Mapper<LongWritable, Text, Text, LongWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        // 将 Text类型转换为String 类型
        String s = value.toString();
        // 安装空格切分
        String[] split = s.split(" ");
        // 循环遍历输出
        for (String s1 : split) {
            // 输出 key=单词 value =1
            context.write(new Text(s1), new LongWritable(1));
        }
    }
}

4.编写Reduce类

package com.czxy.wordCount;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class WordCountReduce extends Reducer<Text, LongWritable,Text,LongWritable> {
    @Override
    protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
        // 定义一个变量用来记录单词出现的次数
        int sumCount=0;
        for (LongWritable value : values) {
            sumCount+=value.get();
        }
        // 结果数据
        context.write(key, new LongWritable(sumCount));
    }
}

5.编写启动类

package com.czxy.wordCount;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class WordCountDriver extends Configured implements Tool {


    @Override
    public int run(String[] args) throws Exception {
        // 获取job
        Job job = Job.getInstance(new Configuration());
        //  设置支持jar执行
        job.setJarByClass(WordCountDriver.class);
        // 设置执行的napper
        job.setMapperClass(WordCountMapper.class);
        // 设置map输出的key类型
        job.setMapOutputKeyClass(Text.class);
        // 设置map输出value类型
        job.setMapOutputValueClass(LongWritable.class);
        // 设置执行的reduce
        job.setReducerClass(WordCountReduce.class);
        // 设置reduce输出key的类型
        job.setOutputKeyClass(Text.class);
        // 设置reduce输出value的类型
        job.setOutputValueClass(LongWritable.class);
        // 设置文件输入
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job, new Path("./data/wordCount/"));
        // 设置文件输出
        job.setOutputFormatClass(TextOutputFormat.class);
        TextOutputFormat.setOutputPath(job, new Path("./outPut/wordCount/"));
        // 设置启动类
        boolean b = job.waitForCompletion(true);
        return b ? 0 : 1;
    }

    public static void main(String[] args) throws Exception {
        // 调用启动方法
        ToolRunner.run(new WordCountDriver(), args);
    }
}

6.执行的结果

MapReduce	1
count	1
hello	2
word	2